ProjectKeeper runs on your own machine — the client starts it, so there is no endpoint to ping. 491 installs a week from npm.
What a project planned, decided and did, for your agents: context packs, notes and the table check.
The linked repository no longer exists on GitHub — it was deleted or made private.
We have not read this server's code yet, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node bin/postinstall.mjs
этот файл ставится пользователю, но в репозитории его нет
const r = spawnSync(process.execPath, [...ENGINE_NODE_FLAGS, ...OWN_TS_NODE_ARGS, CHILD, ...args], {
const versions = all<{ repo: string; blob: string; at: string; import_root: number }>(`SELECT repo, blob, at, import_root FROM docs WHERE path = ?${rel.repo ? ' AND repo = ?' : ''} ORDER BY at_ms`, ...(rel.repo ? [rel.path, rel.repo] : [rel.path]));
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add projectkeeper -- npx -y projectkeeper
{
"mcpServers": {
"projectkeeper": {
"command": "npx",
"args": [
"-y",
"projectkeeper"
]
}
}
}
[mcp_servers.projectkeeper]
command = "npx"
args = ["-y", "projectkeeper"]
{
"mcpServers": {
"projectkeeper": {
"command": "npx",
"args": [
"-y",
"projectkeeper"
]
}
}
}
{
"servers": {
"projectkeeper": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"projectkeeper"
]
}
}
}
Local deterministic project memory for AI agents with context packs, gates and checkpoints.
Your AI agent decides what to enter. OpenAdapt enters it in the app and checks that it saved.
Your why agent, the infra agent for your fleet. Your agents work from what you decided, and why.
An MCP server that provides DevOps and DevSecOps context for the project
Rules-based context reduction, planning checks, research prompts and fixed experiences for agents.
19 date-aware checks on the [project] metadata that decides whether your next release uploads
Shared project context for AI agents and teams: docs, tasks, and messages that stay current.
Your project's design system for coding agents: tokens, components, contrast checks, guidelines.
Answers built from our own checks of this server.